Update README.md

README.md

@@ -68,7 +68,7 @@ from datasets import load_dataset
 
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
-test_dataset = load_dataset("common_voice", "lt", split="test[:2%]").
+test_dataset = load_dataset("common_voice", "lt", split="test[:2%]")
 
 processor = Wav2Vec2Processor.from_pretrained("DeividasM/wav2vec2-large-xlsr-53-lithuanian")
 
@@ -82,11 +82,11 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 def speech_file_to_array_fn(batch):
 
-	speech_array, sampling_rate = torchaudio.load(batch["path"])
+\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
 
-	batch["speech"] = resampler(speech_array).squeeze().numpy()
+\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
 
-	return batch
+\treturn batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 
@@ -94,7 +94,7 @@ inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tens
 
 with torch.no_grad():
 
-	logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
 predicted_ids = torch.argmax(logits, dim=-1)
 
@@ -130,7 +130,7 @@ model = Wav2Vec2ForCTC.from_pretrained("DeividasM/wav2vec2-large-xlsr-53-lithuan
 
 model.to("cuda")
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]'
 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
@@ -140,13 +140,13 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 def speech_file_to_array_fn(batch):
 
-	batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
 
-	speech_array, sampling_rate = torchaudio.load(batch["path"])
+\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
 
-	batch["speech"] = resampler(speech_array).squeeze().numpy()
+\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
 
-	return batch
+\treturn batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 
@@ -156,17 +156,17 @@ test_dataset = test_dataset.map(speech_file_to_array_fn)
 
 def evaluate(batch):
 
-	inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
 
-	with torch.no_grad():
+\twith torch.no_grad():
 
-		logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+\t\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
 
     pred_ids = torch.argmax(logits, dim=-1)
 
-	batch["pred_strings"] = processor.batch_decode(pred_ids)
+\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
 
-	return batch
+\treturn batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)